© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1551
    Prev
    Next
    INDEX
    Explanations

    defines or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <start_of_image>
    0.87
    brook
    0.82
     nonetheless
    0.77
    으니까
    0.76
    linien
    0.74
     ấy
    0.74
    oughby
    0.73
    broke
    0.71
    matu
    0.71
    linie
    0.71
    POSITIVE LOGITS
     Returns
    1.85
     {@
    1.78
     Creates
    1.74
     Defines
    1.73
     Specifies
    1.70
     Determines
    1.70
     用于
    1.69
    Returns
    1.66
     Used
    1.64
     Allows
    1.64
    Activations Density 0.114%

    No Known Activations